Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2317 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.4142. Min Act: -0.1700
Data Index: 398456 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.3830. Min Act: -0.1700
Data Index: 2109831 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.3830. Min Act: -0.1700
Data Index: 984506 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.2892. Min Act: -0.1700
Data Index: 6711713 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.2892. Min Act: -0.1700
Data Index: 6991947 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.2267. Min Act: -0.1700
Data Index: 4009871 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.2580. Min Act: -0.1700
Data Index: 5772894 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.2580. Min Act: -0.1700
Data Index: 587000 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.2892. Min Act: -0.1700
Data Index: 6712829 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.2267. Min Act: -0.1700
Data Index: 66888 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.1955. Min Act: -0.1700
Data Index: 554472 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.1642. Min Act: -0.1700
Data Index: 4591767 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.1642. Min Act: -0.1700
Data Index: 3972078 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.1330. Min Act: -0.1700
Data Index: 2971535 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.1330. Min Act: -0.1700
Data Index: 194251 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.1642. Min Act: -0.1700
Data Index: 279973 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.1017. Min Act: -0.1700
Data Index: 8779650 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.1330. Min Act: -0.1700
Data Index: 8778838 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.0392. Min Act: -0.1700
Data Index: 8341870 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4142. Min Range: -6.4142
Max Act: 6.0705. Min Act: -0.1700
Data Index: 5726235 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19